Call for Papers

Important dates

• • Paper submission deadline: November 17th, 2026
  • Paper notification: January 8th, 2027
  • Camera-ready deadline: February 2nd, 2027

Call for Papers

PeRConAI will focus on solutions that contribute to advancing truly pervasive and liquid AI, enabling edge devices, regardless of their available resources, to accomplish training and inference under full, weak, or no supervision.

The increasing pervasiveness of edge devices and the high availability, velocity, and volatility of data generated and collected at the edge of the internet are pushing towards a paradigm shift in the design of AI-based systems. AI systems are moving the execution of both training and inference tasks from powerful and remote data centers where all data is available in a centralized fashion to more pervasive and distributed/decentralized systems at the edge of the internet, working in proximity to where data is physically generated and/or collected.
The design of edge AI systems must leverage the collaboration of several heterogeneous devices working in a highly dynamic context in terms of processing capabilities and connectivity. Beyond resource limitations, data locally collected or generated by devices might statistically differ from one device to another, even if collected by the same application or belonging to the same phenomenon. Finally, human intervention in the AI process is still predominant, especially in its initial phases, e.g., data preparation, labeling, and pre-processing, thus limiting the necessary speed up to make AI truly pervasive.

Topics of interest

The PeRConAI workshop aims to foster the development and circulation of new ideas and research directions on pervasive and resource-constrained AI/ML, bringing together practitioners and researchers working on the intersection between pervasive computing and machine learning.
The PeRConAI workshop solicits contributions on, but not limited to, the following topics:

** Foundations of Advanced Machine learning algorithms and methods for pervasive systems subject to resource limitations addressing the following open challenges:

– Distributed, decentralized, federated, split, and collaborative learning.
– Resource-efficient training and inference under compute, memory, energy, bandwidth, and latency constraints.
– Model compression and acceleration, including quantization, pruning, distillation, sparsification, and early exiting.
– TinyML and embedded AI for sensors, microcontrollers, wearables, mobile devices, and edge nodes.
– Efficient foundation and generative models for edge and pervasive systems.
– On-device adaptation, personalization, online learning, continual learning, and lifelong learning.
– Self-supervised, semi-supervised, weakly supervised, and unsupervised learning at the edge.
– Robust learning under non-IID, noisy, unreliable, incomplete, or adversarial data.
– Privacy-preserving, secure, trustworthy, explainable, and fair AI for constrained scenarios.
– Energy-aware, carbon-aware, and sustainable AI across the cloud-edge-device continuum.
– Bio-inspired, neuromorphic, spiking, reservoir-computing, and event-driven learning.
– Efficient sequence, state-space, graph, physics-informed, and hybrid learning models.
– Data, model, and workload orchestration across cloud, fog, edge, mobile, and IoT systems.
– Benchmarks, datasets, testbeds, metrics, and reproducibility for constrained pervasive AI.

** Applications of Advanced Machine learning algorithms, methods, and approaches for pervasive computing under resource limitations applied to the following application domains:

– Health, well-being, assisted living, rehabilitation, and personalized care.
– Wearable, mobile, and human-centric sensing.
– Smart homes, smart buildings, and ambient intelligence.
– Industrial IoT, Industry 4.0/5.0, predictive maintenance, robotics, and digital twins.
– Cybersecurity, privacy, safety, intrusion detection, and authentication.
– Audio, speech, acoustic sensing, keyword spotting, and sound event detection.
– Computer vision and video analytics on constrained devices.
– Wireless, RF, mmWave, and communication-aware sensing.
– Smart cities, urban sensing, mobility analysis, and infrastructure monitoring.
– Intelligent transportation, connected vehicles, UAVs, and autonomous systems.
– Environmental monitoring, smart agriculture, energy, and sustainability.
– Remote sensing, satellite edge computing, and Earth observation.
– On-device NLP, information retrieval, and conversational systems.
– Education, cultural heritage, and social-good applications.
– Real-world prototypes, deployments, datasets, benchmarks, and lessons learned.

Submissions Guidelines

All papers must be at most 6 pages of technical content (with the option to include 1 additional page for a maximum of 7 pages total), typeset in double-column IEEE format using 10pt fonts on US letter paper, with all fonts embedded. In PeRConAI, the peer-review process will be double-blind.
Submissions must be made via EDAS. The IEEE LaTeX and Microsoft Word templates and related information can be found on the IEEE Computer Society website.

PeRConAI will be held in conjunction with IEEE PerCom 2027 (https://www.percom.org). All accepted papers will be included in the Percom workshop proceedings and indexed in the IEEEXplore digital library. Each accepted paper
requires full PerCom registration (no student rate). All paper presentations must be delivered in person by one of the authors.

**Important: papers without a valid full registration or that are not presented in-person will be excluded from the proceedings.**

Submission link: TBD 

Steering Committee

• • Prof. Plamen Angelov, Lancaster University, UK
  • Dr. Lorenzo Valerio, CNR-IIT, IT
  • Dr. Paolo Dini, CTTS, ES
  • Prof. Riccardo Pecori, eCampus University and IMEM-CNR, IT

Workshop Organizers

• • Dr. Franco Maria Nardini, CNR-ISTI, IT
  • Prof. Mario Luca Bernardi, University of Sannio, IT
  • Dr. Lorenzo Valerio, CNR-IIT, IT
    Dr. Paolo Dini, CTTC, ES